© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66420
    Prev
    Next
    INDEX
    Explanations

    volume numbering in citations

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron is effectively inactive and does not detect any specific pattern.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    除了
    -1.94
    there
    -1.93
     hubiese
    -1.90
    就在
    -1.90
     verbess
    -1.88
    0
    -1.85
    之前
    -1.82
    ៹
    -1.79
    基本
    -1.79
     There
    -1.73
    POSITIVE LOGITS
    孥
    2.08
    哙
    2.05
    ピアス
    1.91
    </strong>
    1.90
    嫆
    1.84
    鉨
    1.82
    𓐍
    1.80
    opheles
    1.80
    𖣔
    1.78
    汌
    1.73
    Activations Density 0.001%

    No Known Activations